When mutation stage messages are dropped I start by looking for GC problems in
the cassandra logs.
You also have some blocked flush writer tasks, which may be due to a large
number of CF's, a large number of secondary indexes, slow disk IO or excessive
use of snapshot / flush. Check the comment
I am running 1.2.4 with Vnodes and have been writing at low volume. I have
doubled the volume and suddenly 3 of my 6 nodes are showing much higher load
than the others (30 vs 3) and tpstats show the mutation stage as completely
full (see below). I did find a FileNotFoundException that I pasted
